Related papers: TRACE: Trajectory-Aware Comprehensive Evaluation f…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies on expert rubrics, manual annotation, and slow pairwise judgments. Automated efforts are…
In quantitative program analysis, values are assigned to execution traces to represent a quality measure. Such analyses cover important applications, e.g. resource usage. Examining all traces is well known to be intractable and therefore…
Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of \textit{deep research} -- a term also adopted by recent models targeting these…
Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed rubrics, failing to evaluate the underlying research process.…
Modeling dynamical systems is crucial across the science and engineering fields for accurate prediction, control, and decision-making. Recently, machine learning (ML) approaches, particularly neural ordinary differential equations (NODEs),…
Applied Behavior Analysis (ABA) is a clinical discipline whose documentation, teaching programs and multi-session behavioral logs, is formulaic and high-volume, yet real session data is HIPAA-protected and bound by professional…
Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various…
Inspired by advances in LLMs, reasoning-enhanced sequential recommendation performs multi-step deliberation before making final predictions, unlocking greater potential for capturing user preferences. However, current methods are…
Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training.…
While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plateaus due to the quality of the tool interfaces these agents…
Kernel traces are sequences of low-level events comprising a name and multiple arguments, including a timestamp, a process id, and a return value, depending on the event. Their analysis helps uncover intrusions, identify bugs, and find…
LLM-based relevance judgment generation has become a crucial approach in advancing evaluation methodologies in Information Retrieval (IR). It has progressed significantly, often showing high correlation with human judgments as reflected in…
As large language models (LMs) advance, there is an increasing need to control their outputs to align with human values (e.g., detoxification) or desired attributes (e.g., personalization, topic). However, autoregressive models focus on…
Drug discovery is a lengthy and resource-intensive process composed of multiple stages. Among these stages, lead optimization plays a critical role in transforming early hit compounds into viable drug candidates. This stage requires…
The electric power sector has seen an increased penetration of renewable energy sources (RESs) that could strain the system reliability due to their inherent uncertainties in availability and controllability. Effective load carrying…
The advancement in Large Language Models has driven the creation of complex agentic systems, such as Deep Research Agents (DRAs), to overcome the limitations of static Retrieval Augmented Generation (RAG) pipelines in handling complex,…
Recent search agents leverage multi-turn reasoning and search tools to achieve strong performance on multi-hop and long-horizon benchmarks. Yet it remains unclear whether they reliably reason across all requirements by tracking, verifying,…
Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource…
Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation. We challenge this assumption by…